feat: add citation functionality to LLM node context handling
Close #27417
[!IMPORTANT]
- Make sure you have read our contribution guidelines
- Ensure there is an associated issue and you have been assigned to it
- Use the correct syntax to link this PR:
Fixes #<issue number>.
Summary
Screenshots
| Before | After |
|---|---|
| ... | ... |
Checklist
- [ ] This change requires a documentation update, included: Dify Document
- [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
- [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
- [x] I've updated the documentation accordingly.
- [x] I ran
dev/reformat(backend) andcd web && npx lint-staged(frontend) to appease the lint gods
Summary of Changes
Hello @liugddx, I'm Gemini Code Assist[^1]! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request enhances the LLM node's context handling by introducing a citation mechanism. It allows the system to automatically embed source markers into the context provided to the LLM and instructs the LLM to utilize these markers in its responses. This feature aims to improve the transparency and verifiability of LLM outputs by directly linking generated content to its original sources.
Highlights
- New Citation Configuration: Introduced a new
citation_enabledboolean field within theContextConfigfor LLM nodes, allowing users to explicitly enable or disable citation functionality. - Contextual Citation Markers: Implemented logic to automatically append
[position]citation markers to content retrieved from context whencitation_enabledis active and position metadata is available. This ensures that source information is directly integrated into the context provided to the LLM. - LLM Citation Instruction: Added a mechanism to inject a specific instruction into the LLM's prompt. This instruction guides the LLM to use the provided
[position]markers when generating responses, promoting accurate source attribution. - Comprehensive Unit Tests: Included a new test file with extensive unit tests covering various scenarios for the citation functionality, including cases with and without citations, missing position metadata, and string-based contexts, ensuring robustness and correctness.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in pull request comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
[^1]: Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.
pin~
I suggest that we go back to the original issue to discuss the implementation of this feature, rather than directly submitting a PR, as this would make code review difficult.